Ontology for Semantic Integration in a Cognitive Surveillance System

The increasing interest in Cognitive Vision Systems (CVS) motivates the apparition of ad-hoc stages designed for the integration of multiple kinds of knowledge. This paper proposes a novel ontology to restrict and integrate high-level semantics for Human Sequence Evaluation (HSE), which targets multilingual capabilities and multipurpose end-user interfaces. The main contributions of this paper are the conception of a neutral semantic layer, which allows to link vision and linguistic domains; and the use of situations instead of verbs as basic elements for an ontological categorization of occurrences. In our approach, the domain has been restricted to outdoor surveilled scenarios, involving interactions among pedestrians, static objects, and vehicular traffic.

[1]  Hans-Hellmut Nagel,et al.  Natural Language Texts for a Cognitive Vision System , 2002, ECAI.

[2]  Heiner Stuckenschmidt,et al.  Handbook on Ontologies , 2004, Künstliche Intell..

[3]  Pau Baiget,et al.  Natural Language Descriptions of Human Behavior from Video Sequences , 2007, KI.

[4]  R. Cucchiara.  Multimedia surveillance systems , 2005, VSSN@MM.

[5]  J.L. Crowley,et al.  Situated Observation of Human Activity , 2005, Computer Vision for Interactive and Intelligent Environment (CVIIE'05).

[6]  Gösta H. Granlund,et al.  Organization of Architectures for Cognitive Vision Systems , 2006, Cognitive Vision Systems.

[7]  Kunio Fukunaga,et al.  Natural Language Description of Human Activities from Video Images Based on Concept Hierarchy of Actions , 2002, International Journal of Computer Vision.

[8]  Jake K. Aggarwal,et al.  Event semantics in two-person interactions , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[9]  Minhua Ma,et al.  Visual Semantics and Ontology of Eventive Verbs , 2004, IJCNLP.

[10]  Tomek Strzalkowski,et al.  From Discourse to Logic , 1991 .

[11]  Leonard Talmy,et al.  Toward a cognitive semantics, Vol. 1: Concept structuring systems. , 2000 .

[12]  Jordi Gonzàlez i Sabaté.  Human sequence evaluation: the key-frame approach , 2005 .

[13]  Hilary Buxton,et al.  Learning and understanding dynamic scene activity: a review , 2003, Image Vis. Comput..

[14]  Thomas R. Gruber,et al.  Toward principles for the design of ontologies used for knowledge sharing? , 1995, Int. J. Hum. Comput. Stud..

[15]  L. Talmy.  Toward a Cognitive Semantics , 2003 .

[16]  Wolfgang Ponweiser,et al.  Contextual Coordination in a Cognitive Vision System for Symbolic Activity Interpretation , 2006, Fourth IEEE International Conference on Computer Vision Systems (ICVS'06).

[17]  Hans-Hellmut Nagel,et al.  Behavioral Knowledge Representation for the Understanding and Creation of Video Sequences , 2003, KI.

[18]  K. Schäfer,et al.  “F-Limette” fuzzy logic programming integrating metric temporal extensions , 1996 .

[19]  Monique Thonnat,et al.  Towards Ontology Based Cognitive Vision , 2004, ICVS.

[20]  Jordi Gonzàlez,et al.  Robust Multiple-People Tracking Using Colour-Based Particle Filters , 2007, IbPRIA.

[21]  Balakrishnan Chandrasekaran,et al.  What are ontologies, and why do we need them? , 1999, IEEE Intell. Syst..